Dual AI suggestions improve radiology resident accuracy on X-rays
Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study
Artificial IntelligenceComputers and Society
Summary
Reading X-rays is tricky, especially for new doctors still learning. The authors studied if AI tools that give two different guesses about what an X-ray shows help beginners do better than AIs that give only one guess. They found that for radiology trainees, having two AI suggestions helped them get the right answer more often, especially when one AI was wrong. But for doctors not specialized in radiology, having two suggestions didn’t make a difference. This means using two AI opinions might help trainees avoid mistakes.
What this means in practice
- •For hospital radiology departments: Incorporate dual-AI suggestion tools to improve diagnostic accuracy of radiology residents interpreting X-rays, reducing errors when AI outputs are incorrect.
- •For radiology training programs: Use dual-suggestion AI systems during resident training to enhance learning and decision-making in radiographic reading.
Authors
Lin Wu, Zhe Xu, Hongyi Wang, Feifei Zhou, Wei Deng, Chunlong Zhang, Yuting Zhu, Kaixiao Chen, Xiao Liang, Chen Yang, Yeyuan Chen, Hao Chen, Fuqing Zhou
Abstract
Purpose: To compare dual- and single-suggestion AI support for radiographic interpretation by residents, particularly when the shared AI suggestion was incorrect. Materials and Methods: This prospective, multicenter, randomized three-arm reader study was conducted at three hospitals in China from July to September 2026 (ChiCTR2600129243). After specialty stratification, 132 residents with fewer than 3 years of clinical experience were randomized 1:1:1 to GPT-5.4 alone (group A), GPT-5.4 plus Kimi-K2.6 (group B), or GPT-5.4 plus Gemini-3.6 Flash (group C); 123 were analyzed. Participants interpreted 60 radiographs before and after AI support. The primary outcome was accuracy change. Welch ANOVA and Holm-adjusted t tests compared support conditions; HC3 linear models assessed specialty interaction. Results: Among 123 residents (mean age, 24.1 years +/- 1.4; 65 women), radiology residents showed greater accuracy improvement with dual- than single-suggestion support (B-A, 6.69 percentage points [95% CI, 0.97-12.40]; C-A, 7.87 percentage points [95% CI, 1.64-14.11]; Holm-adjusted P = .030 for both), whereas accuracy change did not differ in non-radiology residents (P = .20). When GPT-5.4 was incorrect, AI-assisted accuracy was higher with dual- than single-suggestion support in radiology residents (40.1% and 40.4% vs 20.0%) and non-radiology residents (31.3% and 31.0% vs 12.1%) (all Holm-adjusted P < .001). The dual-suggestion effect differed by specialty (interaction difference, 10.44 percentage points; 95% CI, 4.36-16.52; P < .001). Conclusion: Dual-suggestion support may mitigate the influence of erroneous AI suggestions, with greater accuracy improvement observed in radiology but not non-radiology residents.